Dataset Information

Prevalence and clinical significance of pleural effusion in patients with acute pulmonary embolism: a retrospective study.

ABSTRACT:

Background

Pleural effusion is observed in a subset of patients with acute pulmonary embolism (APE) and may be linked to clinical outcome, but findings from previous studies have been inconsistent. This study aimed to investigate the prevalence and clinical significance of pleural effusion in Chinese patients with APE.

Methods

Clinical data from hospitalized patients with APE were retrospectively collected and the prevalence of pleural effusion was determined. The relationship between the presence of pleural effusion and clinical outcome of APE was analyzed by Cox proportional hazards regression and Kaplan-Meier survival analysis.

Results

The study enrolled 635 patients with APE. The prevalence of pleural effusion was 57.01% (362/635). Patients with pleural effusion had significantly higher in-hospital mortality (9.9% vs. 4.8%, P<0.05) and longer length of hospital stay (LOS) (19.99 vs. 15.31 days, P<0.05) than whose without pleural effusion. However, pleural effusion was not an independent risk factor for in-hospital mortality in patients with APE by multivariate Cox proportional hazards regression analysis [hazard ratio (HR) =1.70, 95% confidence interval (CI): 0.73-3.92, P=0.216] and Kaplan-Meier survival analysis (P=0.174).

Conclusions

Pleural effusion is a frequent occurrence in patients with APE and therefore merits greater attention from clinicians; however, it is not an independent risk factor for in-hospital mortality.

SUBMITTER: Zhang J

PROVIDER: S-EPMC7947497 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prevalence and clinical significance of pleural effusion in patients with acute pulmonary embolism: a retrospective study.

Zhang Jiarui J Zhou Haixia H Aili Adila A Wang Maoyun M Shen Yongchun Y Yi Qun Q

Journal of thoracic disease 20210201 2

<h4>Background</h4>Pleural effusion is observed in a subset of patients with acute pulmonary embolism (APE) and may be linked to clinical outcome, but findings from previous studies have been inconsistent. This study aimed to investigate the prevalence and clinical significance of pleural effusion in Chinese patients with APE.<h4>Methods</h4>Clinical data from hospitalized patients with APE were retrospectively collected and the prevalence of pleural effusion was determined. The relationship bet ...[more]

PMID: 33717527

Similar Datasets

Project description:IntroductionThe characteristics and clinical relevance of pleural effusion (PLEF) in acute pulmonary embolism (APE) are not fully understood.MethodsA single-centre, retrospective study was performed of patients admitted with APE classified according to the subsequent development or not of PLEF. A model was built to predict PLEF and its impact on 30-day all-cause mortality was investigated.ResultsA total of 1602 patients with APE were included (median age, 74 (61, 82) years; 674 men (42.1%); 382 (23.8%) with PLEF). PLEF was associated with a higher number of comorbidities (p=0.015); more peripheral APE (0.001); a higher frequency of pulmonary infarctions (p<0.001) and higher 30-day all-cause mortality (p=0.004) compared with those without PLEF. Bilateral PLEFs, as compared with unilateral, were associated with a higher number of comorbidities (p=0.009); more severe (simplified Pulmonary Embolism Severity Index ≥1; p<0.001) and higher 30-day all-cause mortality (p<0.001).On multivariate analysis, the presence of PLEF was associated with atrial fibrillation (OR 2.00; 95% CI 1.32 to 3.02), congestive heart failure (OR 3.00; 95% CI 1.81 to 5.00), pulmonary infarction (OR 3.19; 95% CI 2.38 to 4.29) and a Charlson index ≥3 (OR 1.59; 95% CI 1.03 to 2.45). The predictive model for PLEF had a moderate power of discrimination (area under the curve, AUC 0.76; 95% CI 0.73 to 0.79), whereas the predictive model for mortality showed a good predictive power (AUC 0.89; 95% CI 0.86 to 0.93). The presence of PLEF doubles the probability of death (OR 2.02; 95% CI 1.11 to 3.68). When PLEF is bilateral, the probability of death is four times higher, as compared with unilateral PLEF (OR 4.07; 95% CI 1.53 to 10.85; AUC 0.90; 95% CI 0.84 to 0.95).ConclusionsA significant number of APE patients develop PLEF. The model showed a good power of discrimination for the prediction of mortality. The probability of death from APE doubles in the presence of PLEF. Patients with APE and concomitant bilateral PLEF have a fourfold higher risk of mortality, as compared with patients with concomitant unilateral PLEF.

Project description:BackgroundTuberculous pleural effusion (TPE) is a challenging extrapulmonary manifestation of tuberculosis, with traditional diagnostic methods often involving invasive surgery and being time-consuming. While various machine learning and statistical models have been proposed for TPE diagnosis, these methods are typically limited by complexities in data processing and difficulties in feature integration. Therefore, this study aims to develop a diagnostic model for TPE using ChatGPT-4, a large language model (LLM), and compare its performance with traditional logistic regression and machine learning models. By highlighting the advantages of LLMs in handling complex clinical data, identifying interrelationships between features, and improving diagnostic accuracy, this study seeks to provide a more efficient and precise solution for the early diagnosis of TPE.MethodsWe conducted a cross-sectional study, collecting clinical data from 109 TPE and 54 non-TPE patients for analysis, selecting 73 features from over 600 initial variables. The performance of the LLM was compared with logistic regression and machine learning models (k-Nearest Neighbors, Random Forest, Support Vector Machines) using metrics like area under the curve (AUC), F1 score, sensitivity, and specificity.ResultsThe LLM showed comparable performance to machine learning models, outperforming logistic regression in sensitivity, specificity, and overall diagnostic accuracy. Key features such as adenosine deaminase (ADA) levels and monocyte percentage were effectively integrated into the model. We also developed a Python package ( https://pypi.org/project/tpeai/ ) for rapid TPE diagnosis based on clinical data.ConclusionsThe LLM-based model offers a non-surgical, accurate, and cost-effective method for early TPE diagnosis. The Python package provides a user-friendly tool for clinicians, with potential for broader use. Further validation in larger datasets is needed to optimize the model for clinical application.

Dataset Information

Prevalence and clinical significance of pleural effusion in patients with acute pulmonary embolism: a retrospective study.

Background

Methods

Results

Conclusions

Publications

Prevalence and clinical significance of pleural effusion in patients with acute pulmonary embolism: a retrospective study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets